Connect
Optimize
Secure
Recruitee MCP Server
for AI Agents
Production-ready Recruitee MCP server with 26 extensible actions — plus built-in authentication, security, and optimized execution.
Recruitee MCP Server
Built by 
StackOne
StackOne 
Coverage
26 Agent Actions
Create, read, update, and delete across Recruitee — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Recruitee MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Recruitee tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.
Prompt Injection Defense →
Performance
Max Agent Context. Min Cost.
Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Recruitee call.
Tools Discovery →What is the Recruitee MCP Server?
A Recruitee MCP server lets AI agents read and write Recruitee data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Recruitee MCP server ships with 26 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, and optimized agent context. Connect it from MCP clients like Claude Desktop, Cursor, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.
All Recruitee MCP Tools and Actions
Every action from Recruitee's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Attachments
- Create Attachment
Upload an attachment from a remote URL
Candidates
- Create Candidate
Create a new candidate record
- List Candidates
Retrieve all candidates in the system
- Get Candidate
Retrieve a single candidate by ID
- Search Candidates
Search candidates with advanced filtering
- Update Candidate
Update an existing candidate's information
- Delete Candidate
Delete a candidate from the system
Candidate CVs
- Update Candidate CV
Update a candidate's CV from a remote URL
Candidate Notes
- List Candidate Notes
Get all notes for a candidate
Candidate Custom Fields
- Create Candidate Custom Field
Add a custom field to a candidate profile
Departments
- List Departments
Retrieve all departments in the company
Partners
- Create Partner
Register a new integration partner
- Get Partner
Retrieve an integration partner by codename
- Update Partner
Update an existing integration partner
- Delete Partner
Delete an integration partner
Regenerate Partner Secrets
- Regenerate Partner Secret
Regenerate the secret key for an integration partner
Locations
- List Locations
Retrieve all company locations
Offers
- Create Offer
Create a new job offer
- List Offers
Retrieve all job offers in the system
- Get Offer
Retrieve a single job offer by ID
- Update Offer
Update an existing job offer
- Delete Offer
Delete a job offer
Reports
- Create Report
Create a new partner report for a candidate
- Update Report
Update a partner report status and details
- Delete Report
Delete a partner report
Candidate Reports
- List Candidate Reports
Get all reports for a candidate
Set Up Your Recruitee MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Recruitee in under 10 lines of code.
MCP Clients
Agent Frameworks
JSON{
"mcpServers": {
"stackone": {
"command": "npx",
"args": [
"-y",
"mcp-remote@latest",
"https://api.stackone.com/mcp?x-account-id=<account_id>",
"--header",
"Authorization: Basic <YOUR_BASE64_TOKEN>"
]
}
}
}More Recruiting MCP Servers
JobAdder
246+ actions
Vincere
206+ actions
SmartRecruiters
164+ actions
Ashby
137+ actions
Factorial
127+ actions
HiBob
123+ actions
HiBob (with Webhooks)
123+ actions
Recruitee MCP Server Resources
MCP Code Mode: Keeping Tool Responses Out of Agent Context
Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.
11 min
Comparing BM25, TF-IDF, and Hybrid Search for MCP Tool Discovery
Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.
10 min
Indirect Prompt Injection Defense for MCP Tools: A Technical Guide
MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.
12 min
Recruitee MCP Server FAQ
Recruitee MCP server vs direct API integration — what's the difference?
A Recruitee MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Recruitee. A Recruitee MCP server is for AI agents — MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI — discovering and calling Recruitee at runtime. StackOne provides both.
How does Recruitee authentication work for AI agents?
Recruitee authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK — you get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own Recruitee account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Recruitee MCP tools vulnerable to prompt injection?
Yes — Recruitee MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content — documents, messages, tickets, records, or free-text fields — is a potential vector. StackOne Defender scans every tool response before it enters the agent's context — regex patterns in ~1ms, then a MiniLM classifier in ~4ms. 88.7% accuracy, CPU-only.
What is the context bloat of a Recruitee agent and how do I avoid it?
Context bloat happens when Recruitee tool schemas and API responses eat your Recruitee agent's memory, preventing it from reasoning effectively. A single Recruitee query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery and Code Mode reduce context bloat — loading only relevant tools per query and keeping raw responses out of the agent's context.
Can I limit which actions my Recruitee agent can access?
Yes — you can limit which actions your Recruitee agent can access directly from the StackOne dashboard. Toggle actions on or off, or restrict them to specific accounts, with no code changes to your agent. Session tokens can be scoped to exact actions so if one leaks, exposure stays contained.
Can I create custom agent actions for my Recruitee MCP server?
Yes — you can create custom agent actions for your Recruitee MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Recruitee's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Recruitee MCP server?
Skip a Recruitee MCP server if your integration is purely software-to-software — direct Recruitee API integration is simpler when no AI agent is involved. For deterministic, compliance-critical operations (financial transactions, regulatory reporting), direct API gives you predictable behavior without agent-driven decision-making. MCP shines when AI agents need to dynamically discover and call Recruitee actions at runtime.
What AI frameworks and AI clients does the StackOne Recruitee MCP server support?
The StackOne Recruitee MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.
Put your AI agents to work
All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.